# Combo of Thinking and Observing for Outside-Knowledge VQA

arXiv: https://arxiv.org/abs/2305.06407 · HTML: https://mlsanity.com/paper/2305.06407/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 72 references that are in the map.
- First posted on arXiv 10 May 2023.

## Builds on (most cited first, 30 of 51)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [Deep Modular Co-Attention Networks for Visual Question Answering](https://mlsanity.com/paper/1906.10770/) (2019)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [Bilinear Attention Networks](https://mlsanity.com/paper/1805.07932/) (2018)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [UNITER: UNiversal Image-TExt Representation Learning](https://mlsanity.com/paper/1909.11740/) (2019)
- [FVQA: Fact-based Visual Question Answering](https://mlsanity.com/paper/1606.05433/) (2016)

## Built on by (most cited first, 9 of 9)

- [Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines](https://mlsanity.com/paper/2502.16641/) (2025)
- [OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval](https://mlsanity.com/paper/2505.07879/) (2025)
- [GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2402.02503/) (2024)
- [Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking](https://mlsanity.com/paper/2307.16806/) (2023)
- [Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA](https://mlsanity.com/paper/2406.12746/) (2024)
- [Object Attribute Matters in Visual Question Answering](https://mlsanity.com/paper/2401.09442/) (2023)
- [From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2511.11132/) (2025)
- [KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering](https://mlsanity.com/paper/2601.11632/) (2026)
- [Online Self-Calibration Against Hallucination in Vision-Language Models](https://mlsanity.com/paper/2605.00323/) (2026)

## Abstract (arXiv)

Outside-knowledge visual question answering is a challenging task that requires both the acquisition and the use of open-ended real-world knowledge. Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features. In this paper, we are inspired to constrain the cross-modality space into the same space of natural-language space which makes the visual features preserved directly, and the model still benefits from the vast knowledge in natural-language space. To this end, we propose a novel framework consisting of a multimodal encoder, a textual encoder and an answer decoder. Such structure allows us to introduce more types of knowledge including explicit and implicit multimodal and textual knowledge. Extensive experiments validate the superiority of the proposed method which outperforms the state-of-the-art by 6.17% accuracy. We also conduct comprehensive ablations of each component, and systematically study the roles of varying types of knowledge. Codes and knowledge data can be found at https://github.com/PhoebusSi/Thinking-while-Observing.